StructTokenBench
A benchmark suite for protein structure tokenizers that integrates multiple downstream tasks and data splits for the horizontal comparison of representation quality across different tokenizers, covering dimensions such as structure reconstruction, function prediction, and retrieval.
Timeline (last 90 days)
On the seven benchmarks, 14 tasks and 28 test splits of StructTokenBench, ProTok achieved an average rank of 1.4 among pure structure tokenizers, ranking first on 21 splits and entering the top two on 27 of the 28 splits.
StructTokenBench is an evaluation benchmark suite for protein structure tokenizers, covering 7 benchmarks, 14 tasks and 28 test splits, with evaluation dimensions including structure reconstruction, function prediction, retrieval and others.
All Facts (2)
On the seven benchmarks, 14 tasks and 28 test splits of StructTokenBench, ProTok achieved an average rank of 1.4 among pure structure tokenizers, ranking first on 21 splits and entering the top two on 27 of the 28 splits.
50%UnverifiedStructTokenBench is an evaluation benchmark suite for protein structure tokenizers, covering 7 benchmarks, 14 tasks and 28 test splits, with evaluation dimensions including structure reconstruction, function prediction, retrieval and others.
50%